# GPT-OSS Safeguard 20B

> OpenAI's open-weight safety reasoning model built on gpt-oss-20b (Apache 2.0). A 21B-parameter MoE tuned for safety tasks: content classification, LLM input/output filtering, and trust & safety judgments with reasoning traces. Use it as a guardrail/judge hop in front of or behind chat models.

**ID**: `openai/gpt-oss-safeguard-20b`  
**Creator**: OpenAI  
**Category**: text  
**Context**: 131K tokens  
**Input**: $0.07/M  
**Output**: $0.30/M  
**Released**: 2025-10-29  
**Web page**: https://anyrouter.dev/model/openai/gpt-oss-safeguard-20b

**Input modalities**: text  
**Output modalities**: text  

**Tokenizer**: GPT

**Capabilities**: chat, reasoning, function-calling, streaming

**Supported parameters**: max_tokens, temperature, top_p, stop

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "openai/gpt-oss-safeguard-20b",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| groq-byok | $0 | $0 |
| openrouter-byok | $0 | $0 |

## Source

- Upstream docs: https://console.groq.com/docs/model/openai/gpt-oss-safeguard-20b